US11696130B2 - Mobile phone authentication method using implicit authentication - Google Patents
Mobile phone authentication method using implicit authentication Download PDFInfo
- Publication number
- US11696130B2 US11696130B2 US17/256,230 US201817256230A US11696130B2 US 11696130 B2 US11696130 B2 US 11696130B2 US 201817256230 A US201817256230 A US 201817256230A US 11696130 B2 US11696130 B2 US 11696130B2
- Authority
- US
- United States
- Prior art keywords
- data
- server
- authentication
- behavior data
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active, expires
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/06—Authentication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/60—Context-dependent security
- H04W12/63—Location-dependent; Proximity-dependent
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/60—Context-dependent security
- H04W12/65—Environment-dependent, e.g. using captured environmental data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/60—Context-dependent security
- H04W12/68—Gesture-dependent or behaviour-dependent
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/025—Services making use of location information using location based information parameters
Definitions
- This disclosure relates to a mobile phone authentication method using implicit authentication, and more particularly, to a technology for identifying and authenticating a user in mobile phone authentication using a short message service (SMS).
- SMS short message service
- an authentication method using a mobile phone is being widely used to identify a user online, such as signing-up for a specific website, payment in an Internet shopping mall or a financial transaction through a financial institution web.
- a resident registration number and a mobile phone number of a user are input into a provided authentication page, and then user authentication is performed by checking the occupancy of user's mobile phone through the input of an authentication number transmitted to the mobile phone of the user.
- the mobile phone authentication system when performing user authentication, provides an authentication page to the user through a web browser or the like, receives user information (a resident registration number, a communication company name, a mobile phone number, or the like) on the provided authentication page, and transmits the received user information to a server.
- user information a resident registration number, a communication company name, a mobile phone number, or the like
- the server accesses a communication company server of the communication company to which the user has subscribed based on the input user information, and compares the input user information with user information such as the resident registration number and the mobile communication terminal number of the user, stored in the communication company server, to determine whether the user information matches. In this case, if it is determined that the user information is matched, a message including an authentication number according to user authentication is sent to a terminal of the user through a mobile communication network of the communication company server.
- this conventional method is very vulnerable to an attack of stealing an SMS authentication by smishing or the like.
- SMS authentication security application APP
- the present disclosure is designed to solve the problems of the conventional mobile phone authentication method as described above, and the present disclosure is directed to providing a mobile phone authentication method using implicit authentication, which enables a user to be identified in authentication of a mobile phone user using an implicit authentication technology.
- a mobile phone authentication method using implicit authentication comprises: by a server, receiving behavior data and environment information data from a user terminal when a user checks an authentication number for authentication of a mobile phone user; by the server, detecting a start point of a behavior of the user for checking the authentication number by performing peak detection in the received behavior data, and storing behavior data from the detected start point; and by the server, extracting feature data from the received environment information data and learning the extracted feature data to build a learning model.
- the behavior data may be three-axis acceleration data of the user terminal and three-axis gyro sensor data of the user terminal, sampled according to a set cycle.
- the step of detecting a start point of a behavior and storing behavior data from the detected start point may include: by the server, normalizing the received behavior data; and calculating a mean value for each data in the behavior data received multiple times.
- the environment information data may include at least one of device information, wireless access point (AP) information. Bluetooth information and GPS information.
- AP wireless access point
- the server may extract the feature data by comparing the received environment information data with environment information data registered previously.
- the learning model may be an auto-encoder type model.
- the method may further comprise: by the server, sending the authentication number and a request for transmission of behavior data and environment information data to the user terminal.
- the behavior data may be received and stored according to each posture of the user terminal classified in advance.
- a mobile phone authentication method using implicit authentication comprises: by a server, receiving a request for authentication of a mobile phone user for a user terminal; by the server, sending an authentication number and a request for transmission of behavior data and environment information data to the user terminal; by the server, determining a posture of the user terminal by using received behavior data; by the server, detecting a start point of a behavior of the user for checking the authentication number by performing peak detection in the received behavior data; by the server, calculating a degree of accordance or discordance by comparing the behavior data from the detected start point with behavior data according to the determined posture of the mobile phone among behavior data stored in advance; by the server, calculating reliability by inputting the received environment information data to a learning model built in advance; and by the server, determining whether user authentication is successful based on the calculated degree of accordance or discordance and the calculated reliability.
- the step of detecting a start point may include by the server, normalizing the received behavior data.
- the server may calculate the degree of accordance or discordance by using dynamic time warping.
- the server may extract feature data from received environment information data and calculate reliability by inputting the extracted feature data to the learning model.
- the mobile phone authentication method using implicit authentication checks whether behavior data and environment information data of the user performing authentication of a mobile phone user are matched with data of a registered user, in order to prevent the user authentication from being passed by fraudulent use of the mobile phone by a person other than the user without requiring an additional operation of the user.
- FIG. 1 is a diagram schematically showing a system in which a mobile phone authentication method using implicit authentication according to an embodiment of the present disclosure is performed.
- FIG. 2 is a flowchart for illustrating an authentication data construction process in the mobile phone authentication method using implicit authentication according to an embodiment of the present disclosure.
- FIGS. 3 to 5 are diagrams for illustrating a behavior data registration process in the mobile phone authentication method using implicit authentication according to an embodiment of the present disclosure.
- FIG. 6 is a diagram for illustrating a process of generating an environment information learning model in the mobile phone authentication method using implicit authentication according to an embodiment of the present disclosure.
- FIG. 7 is a flowchart for illustrating a mobile phone authentication method using implicit authentication according to an embodiment of the present disclosure.
- FIG. 1 is a diagram schematically showing a system in which a mobile phone authentication method using implicit authentication according to an embodiment of the present disclosure is performed.
- a mobile phone authentication method using implicit authentication is performed by interaction between a user terminal 100 and a server 200 .
- the user terminal 100 may be a mobile phone of a user and may include a smart watch of the user terminal 100 if the mobile phone is interlocked with the smart watch.
- the server 200 may be an authentication server that performs identification of a mobile phone user.
- a website server for providing an authentication page may operate in connection with the above configuration.
- a communication company server for checking user authentication information, or the like may operate in connection with the above configuration.
- the user terminal 100 may be configured to transmit behavior data of the user (or, user behavior data) and environment information data to the server 200 .
- the user behavior data may be data output from an acceleration sensor (a sensor that measures the acceleration of the mobile phone itself) and a gyro sensor of the mobile phone.
- the user behavior data is data about the behavior performed by the user to check an authentication number
- implicit authentication is performed using a behavior pattern of the user when the user checks the authentication number.
- the acceleration sensor and the gyro sensor of the mobile phone may be a 3-axis acceleration sensor and a 3-axis gyro sensor, respectively.
- the environment information data is data about the surrounding environment where mobile phone authentication is performed and the user terminal 100 , and may include device information (a brand, a manufacturer, a device model, a serial number, or the like), wireless access point (AP) information, Bluetooth information, GPS information, and the like.
- device information a brand, a manufacturer, a device model, a serial number, or the like
- AP wireless access point
- Bluetooth information a GPS information, and the like.
- the user terminal 100 may be configured to transmit the above information to the server 200 according to a request of the server 200 .
- an application (APP) for transmitting the above information may be installed at the user terminal 100 , or the user terminal 100 may also be equipped with the information transmission function when being shipped.
- FIG. 2 is a flowchart for illustrating an authentication data construction process in the mobile phone authentication method using implicit authentication according to an embodiment of the present disclosure
- FIGS. 3 to 5 are diagrams for illustrating a behavior data registration process in the mobile phone authentication method using implicit authentication according to an embodiment of the present disclosure
- FIG. 6 is a diagram for illustrating a process of generating an environment information learning model in the mobile phone authentication method using implicit authentication according to an embodiment of the present disclosure. The user registration process for mobile phone will be described with reference to FIGS. 2 to 6 .
- the server 200 may provide a user registration webpage or the like so that an operation such as mobile phone user authentication may be performed later. That is, the user may perform user registration by entering an authentication number on a user registration webpage through an authentication number verification process, and this user registration process may be performed in the form of collecting data multiple times for each posture of the user terminal 100 .
- an acceleration sensor value and a gyro sensor value may be used as the user behavior data, and these data may be differently represented for each posture of the user terminal 100 .
- a plurality of postures of the user terminal 100 may be classified in advance, and the user behavior data may be registered for each posture.
- the posture of the user terminal 100 may be classified into a case where the mobile phone is placed on an object such as a table, a case where the user is holding the mobile phone in hand, a case where the authentication process is performed through the mobile phone in the pocket of the user, or the like, and the user may proceed with user registration by performing an action according to each posture set in advance.
- the server 200 transmits an authentication number and a signal for requesting behavior data and environment information data to the user terminal 100 , and the user may perform an action according to the designated posture of the mobile phone to check the authentication number so that user registration is performed.
- the server 200 receives user behavior data and environment information data for each posture of the mobile phone from the user terminal 100 (S 200 ). That is, the server 200 collects behavior data and environment information data as described above for user registration.
- the user terminal 100 may sample data according to a preset cycle (e.g., 10 ms) and transmit the data to the server 200 .
- a preset cycle e.g. 10 ms
- the server 200 detects a start point of the behavior of the user to check the authentication number through peak detection in the received behavior data, and stores the behavior data from the detected start point (S 210 ).
- This behavior data registration process will be described as follows with reference to FIGS. 3 to 5 .
- the server 200 may process the received data to perform data comparison and analysis, and as shown in FIG. 3 , the server 200 may normalize the received behavior data first. That is, the server 200 may convert sensor data into a value between 0 and 1 by performing maximum and minimum scaling (Min Max Scaling).
- the server 200 may calculate a mean value for each data (x-axis, y-axis and z-axis acceleration sensor values and x-axis, y-axis and z-axis gyro sensor values) from the received behavior data (or the normalized behavior data), and perform data processing using the calculated mean value. That is, as described above, the behavior data may be received multiple times for each posture of the mobile phone, so the data may be processed through averaging.
- the server 200 may detect the start point of the behavior of the user to check the authentication number through peak detect in the data processed with the mean value.
- the peak detection may be performed by detecting a point in which the rate of change of data is equal to or greater than a preset reference value, comparing a mean rate of change of data in a certain region with a reference value, or the like, and various other methods may also be used.
- the server 200 may store the behavior data from the detected start point.
- the server 200 may set a peak point as the start point, but in order to prevent data loss related to the behavior of the user to verify the authentication number, the server 200 may also set a point before a certain number (e.g., 4) as the start point of the behavior.
- the behavior data may be stored for each posture of the mobile phone.
- the server 200 extracts feature data from the received environment information data, and inputs the extracted feature data to an auto-encoder (AE) to perform learning (S 220 ).
- AE auto-encoder
- the environment information data is data about the surrounding environment where the mobile phone authentication is performed and the user terminal 100 , and may include device information (a brand, a manufacturer, a device model, a serial number, or the like), wireless access point (AP) information (BSSID (MAC address of the wireless AP). RSSI (signal intensity)), Bluetooth information (MAC address, RSSI). GPS information (latitude, longitude), and the like.
- device information a brand, a manufacturer, a device model, a serial number, or the like
- AP wireless access point
- RSSI signal intensity
- Bluetooth information MAC address, RSSI
- GPS information latitude, longitude
- the server 200 first processes the environment information data to extract feature data.
- the server 200 may extract a character string that combines the brand, the manufacturer and the device model name, BSSID of three wireless APs with strong signal strength and RSSI thereof, Bluetooth MAC of the user terminal 100 , or the like.
- the server 200 may register the character string that combines the brand, the manufacturer and the device model name, the BSSID of three wireless APs with strong signal strength, the Bluetooth MAC of the user terminal 100 , or the like, in order to extract feature data.
- the server 200 extracts feature data by comparing previously registered environment information data with the newly inputted environment information data.
- the server 200 may extract 100 as feature data, and if they are not matched, the server 200 may extract 0 as the feature data.
- RSSI for the corresponding BSSID may be extracted as feature data, and if not registered, ⁇ 100 may be extracted as feature data.
- RSSI for the MAC may be extracted as feature data, and if not registered, ⁇ 100 may be extracted as feature data.
- the latitude and longitude of the user terminal 100 may be extracted as feature data as they are.
- the server 200 may configure a feature vector of the extracted environment information and learn the feature vector to generate a learning model. In this way, the server 200 may generate and store a learning model for the environment information.
- the server 200 may perform environment information authentication using a deep learning technique, and specifically, the server 200 may construct an auto-encoder (AE) model by learning the extracted feature vector.
- AE auto-encoder
- the AE has a structure as shown in FIG. 6 and is a type of FNN (Feedforward Neural Network), which is a neural network that learns inherent characteristics of data.
- the AE is a learning model that is trained to generate an output value similar to an input value, and the AE generates an output value with high similarity for an input value similar to the learned data, but an output value for an input value that is not similar to the learned data has low similarity.
- h ⁇ 1 ( Wx+b )
- z ⁇ 2 ( W′h+b ′)
- L ( x,z ) ⁇ x ⁇ 2 ( W ′( ⁇ 1 ( Wx+b ))+ b ′) ⁇ 2 [Equation 1]
- Equation 1 The learning method of the AE may be explained using Equation 1.
- h is a result obtained by encoding input data x through the AE
- z is a result obtained by decoding h
- ⁇ 1 and ⁇ 2 are activation functions
- L is a loss function.
- the learning process of the AE in this equation is a process of finding W and W′ that minimizes the loss function, and if similar data are repeatedly input. W and W′ corresponding to the characteristics of the data may be calculated.
- the AE outputs data with high similarity between the input value and the output value for the input value similar to the learned data, but for input values not similar to the learned data, the AE outputs data with low similarity between the input value and the output value, i.e., with high dissimilarity.
- the input environment data is registered in the server 200 , and environment information input for the first time may be processed as all features are matched.
- the learning model may be configured to continuously learn data inputted during mobile phone authentication, explained later.
- the order of the step S 210 and the step S 220 is not fixed, so the order of the steps may be changed or both steps may be simultaneously performed in parallel.
- FIG. 7 is a flowchart for illustrating a mobile phone authentication method using implicit authentication according to an embodiment of the present disclosure.
- the server 200 when a request for authentication of a mobile phone for the user terminal 100 is received (S 300 ), the server 200 sends an authentication number to the corresponding user terminal 100 and requests transmission of behavior data and environment information data (S 310 ). That is, if there is a request for authentication of the mobile phone, the server 200 may transmit the authentication number to the user terminal 100 and also request for transmission of data required for determining whether the user is a legitimate user. At this time, the behavior data and the environment information data may be requested and received in the same manner as the user registration process of FIG. 2 described above.
- the server 200 determines the posture of the mobile phone using the received behavior data (S 320 ). That is, since the trend of the behavior data is shown differently according to each posture of the mobile phone, the server 200 may analyze the behavior data and determine the posture of the mobile phone as one of preset postures.
- the posture may be analyzed through supervised learning machine learning using a support vector machine (SVM).
- SVM support vector machine
- the server 200 detects a start point of the behavior taken by the user to check the authentication number through peak detection for the behavior data (S 330 ).
- the server 200 may detect the start point of the behavior performed by the user to check the authentication number in the same manner as the step S 210 described above, and for this purpose, the server 200 may perform a data normalization process.
- the server 200 compares the received behavior data with behavior data stored for the determined posture of the mobile phone by means of dynamic time warping (DTW) (S 340 ).
- DTW dynamic time warping
- the server 200 may numerically calculate the degree of accordance or discordance between both data by comparing behavior data corresponding to the determined posture of the mobile phone among behavior data stored for each posture of the mobile phone with the data after the behavior start point in the received behavior data.
- the server 200 may calculate the degree of accordance or discordance between both data sets by using the DTW as described above, as will be described below more specifically.
- the (i, j) th element of the matrix contains the distance between two points r i and s j .
- the warping path W is defined as a contiguous set of matrices defined by the mapping between R and S.
- K in the denominator is used to compensate for the fact that the warping path can have various lengths.
- Equation 3 defining the distance d(i, j) found in a current cell and ⁇ (i, j), which is the minimum cumulative distance of adjacent elements.
- ⁇ ( i,j ) d ( r i ,s j )+min( ⁇ ( i ⁇ 1, j ⁇ 1), ⁇ ( i ⁇ 1, j ), ⁇ ( i,j ⁇ 1)) [Equation 3]
- the server 200 may calculate the DTW value for each data (x-axis, y-axis and z-axis acceleration sensor values and x-axis, y-axis and z-axis gyro sensor values) and calculate the sum of them.
- the sum calculated in this way is expressed as S_DTW.
- the server 200 calculates reliability by inputting the received environment information data into the learning model (S 350 ).
- the server 200 may calculate reliability by extracting feature data from the received environment information data and inputting the extracted feature data into the learning model built in the step S 220 .
- the process of extracting the feature data may be the same as the above step S 220 .
- This reliability may be calculated as in Equation 4, where loss c is the loss for newly entered environment data and max(loss e ) is the maximum loss that can be obtained by inputting a feature vector, extracted when the received environment information data and registered environment information data are not entirely matched, into the user environment model.
- the loss may be a mean squared error of the value output from the learning model and the value input to the learning model, but it is also possible to use various values capable of representing dissimilarity between the value output from the learning model and the value input to the learning model as the loss value.
- the server 200 determines whether the authentication is successful by combining the DTW result of the step S 340 with the reliability calculated in the step S 350 (S 360 ).
- the server 200 may determine that user authentication fails, and processes as authentication failure (even if the user inputs the correct authentication number).
- the server 200 may process as an authentication success, and if the calculated value (score) is larger than the predefined threshold, the server 200 may process as an authentication failure.
- step S 320 and the step S 330 may be performed simultaneously or sequentially regardless of the order, and the step S 340 and the step S 350 may also be performed simultaneously or sequentially regardless of the order.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Animal Behavior & Ethology (AREA)
- Human Computer Interaction (AREA)
- Social Psychology (AREA)
- Environmental & Geological Engineering (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Telephonic Communication Services (AREA)
- Telephone Function (AREA)
Abstract
Description
h=σ 1(Wx+b),
z=σ 2(W′h+b′),
L(x,z)=∥x−σ 2(W′(σ1(Wx+b))+b′)∥2 [Equation 1]
γ(i,j)=d(r i ,s j)+min(γ(i−1,j−1),γ(i−1,j),γ(i,j−1)) [Equation 3]
Claims (7)
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020180148513A KR102081266B1 (en) | 2018-11-27 | 2018-11-27 | Authentication method of mobile phone using implicit authentication |
KR10-2018-0148513 | 2018-11-27 | ||
PCT/KR2018/016966 WO2020111377A1 (en) | 2018-11-27 | 2018-12-31 | Mobile phone authentication method using implicit authentication |
Publications (2)
Publication Number | Publication Date |
---|---|
US20210266740A1 US20210266740A1 (en) | 2021-08-26 |
US11696130B2 true US11696130B2 (en) | 2023-07-04 |
Family
ID=69647775
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US17/256,230 Active 2039-10-25 US11696130B2 (en) | 2018-11-27 | 2018-12-31 | Mobile phone authentication method using implicit authentication |
Country Status (3)
Country | Link |
---|---|
US (1) | US11696130B2 (en) |
KR (1) | KR102081266B1 (en) |
WO (1) | WO2020111377A1 (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20130128089A (en) | 2012-05-16 | 2013-11-26 | 효성에프엠에스 주식회사 | An authentication system using mobile phone and the authentication method |
US20140020058A1 (en) * | 2012-07-11 | 2014-01-16 | Conor Robert White | Methods and systems for improving the security of secret authentication data during authentication transactions |
US20140283022A1 (en) * | 2012-07-11 | 2014-09-18 | Jason Chris BELONCIK | Methods and sysems for improving the security of secret authentication data during authentication transactions |
KR20140139451A (en) | 2014-10-24 | 2014-12-05 | 김혁 | Athentication System using mobile device and method thereof |
KR20150019125A (en) | 2013-08-12 | 2015-02-25 | 한국전자통신연구원 | Authentication apparatus based onfg motion |
US20170227995A1 (en) * | 2016-02-09 | 2017-08-10 | The Trustees Of Princeton University | Method and system for implicit authentication |
-
2018
- 2018-11-27 KR KR1020180148513A patent/KR102081266B1/en active IP Right Grant
- 2018-12-31 US US17/256,230 patent/US11696130B2/en active Active
- 2018-12-31 WO PCT/KR2018/016966 patent/WO2020111377A1/en active Application Filing
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20130128089A (en) | 2012-05-16 | 2013-11-26 | 효성에프엠에스 주식회사 | An authentication system using mobile phone and the authentication method |
US20140020058A1 (en) * | 2012-07-11 | 2014-01-16 | Conor Robert White | Methods and systems for improving the security of secret authentication data during authentication transactions |
US20140283022A1 (en) * | 2012-07-11 | 2014-09-18 | Jason Chris BELONCIK | Methods and sysems for improving the security of secret authentication data during authentication transactions |
KR20150019125A (en) | 2013-08-12 | 2015-02-25 | 한국전자통신연구원 | Authentication apparatus based onfg motion |
KR20140139451A (en) | 2014-10-24 | 2014-12-05 | 김혁 | Athentication System using mobile device and method thereof |
US20170227995A1 (en) * | 2016-02-09 | 2017-08-10 | The Trustees Of Princeton University | Method and system for implicit authentication |
Non-Patent Citations (3)
Title |
---|
Centeno, Mario Panetto et al., "Smartphone Continuous Authentication Using Deep Learning Autoencoders", IEEE 2017 15th PST. Aug. 28, 2017. |
Lee, Wei-Han et al., "Multi-sensor Authentication to Improve Smartphone Security", IEEE 2015 ICISSP, Feb. 9, 2015. |
Llee, Wei-Han et al., "Secure Pick Up: Implicit Authentication When You Start Using the Smartphone", ACM SACMAT'17, Jun. 21, 2017. |
Also Published As
Publication number | Publication date |
---|---|
KR102081266B1 (en) | 2020-02-25 |
US20210266740A1 (en) | 2021-08-26 |
WO2020111377A1 (en) | 2020-06-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10706850B2 (en) | Location based voice association system | |
US9892732B1 (en) | Location based voice recognition system | |
US10789343B2 (en) | Identity authentication method and apparatus | |
AU2017316312B2 (en) | Remote usage of locally stored biometric authentication data | |
US9848298B2 (en) | System and method for automated analysis comparing a wireless device location with another geographic location | |
EP2130357B1 (en) | Method for tracking credit card fraud | |
US10922677B2 (en) | Service implementation using a graphic code including a biometric identifier | |
JP2022513977A (en) | Identity identification method, device and server for designated point approval | |
US20090320123A1 (en) | Method and apparatus for user recognition employing motion passwords | |
US20140279113A1 (en) | System and Method to Reduce Misuse of a Financial Instrument at a Point-of-Sale Location | |
WO2014201780A1 (en) | Method, apparatus and system for payment validation | |
JP7213596B2 (en) | Identification method, device and server based on dynamic rasterization management | |
US20150142439A1 (en) | System and method of speaker recognition | |
US20220164423A1 (en) | Method and apparatus for user recognition | |
US20230027527A1 (en) | Identity authentication method, and method and apparatus for training identity authentication model | |
Gurulian et al. | On the effectiveness of ambient sensing for detecting NFC relay attacks | |
US11696130B2 (en) | Mobile phone authentication method using implicit authentication | |
CN113542393B (en) | Data transmission method and device | |
KR102242949B1 (en) | Wireless Communication Device Authentication Method and Apparatus using Deep Learning | |
US11202205B2 (en) | Computer-implemented identification method | |
CN115019790A (en) | Resource transfer method and related device | |
CN112733116A (en) | Method, system and device for identity authentication |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: FOUNDATION OF SOONGSIL UNIVERSITY-INDUSTRY COOPERATION, KOREA, REPUBLIC OF Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:CHOI, DAE SEON;REEL/FRAME:054750/0679 Effective date: 20201221 |
|
FEPP | Fee payment procedure |
Free format text: ENTITY STATUS SET TO UNDISCOUNTED (ORIGINAL EVENT CODE: BIG.); ENTITY STATUS OF PATENT OWNER: SMALL ENTITY |
|
FEPP | Fee payment procedure |
Free format text: ENTITY STATUS SET TO SMALL (ORIGINAL EVENT CODE: SMAL); ENTITY STATUS OF PATENT OWNER: SMALL ENTITY |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |